EP3846405B1 - Method for processing tcp message, toe assembly, and network device - Google Patents

Method for processing tcp message, toe assembly, and network device Download PDF

Info

Publication number
EP3846405B1
EP3846405B1 EP19867965.6A EP19867965A EP3846405B1 EP 3846405 B1 EP3846405 B1 EP 3846405B1 EP 19867965 A EP19867965 A EP 19867965A EP 3846405 B1 EP3846405 B1 EP 3846405B1
Authority
EP
European Patent Office
Prior art keywords
storage
tcp
storage address
address
block
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP19867965.6A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP3846405A4 (en
EP3846405A1 (en
Inventor
Qikun Wei
Mingli ZHANG
Yanfei HAN
Hongbo ZHAO
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of EP3846405A1 publication Critical patent/EP3846405A1/en
Publication of EP3846405A4 publication Critical patent/EP3846405A4/en
Application granted granted Critical
Publication of EP3846405B1 publication Critical patent/EP3846405B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/161—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
    • H04L69/162—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields involving adaptations of sockets based mechanisms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/163—In-band adaptation of TCP data exchange; In-band control procedures
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/19—Flow control; Congestion control at layers above the network layer
    • H04L47/193—Flow control; Congestion control at layers above the network layer at the transport layer, e.g. TCP related
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/12—Protocol engines
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
    • H04L69/166—IP fragmentation; TCP segmentation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/22—Parsing or analysis of headers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/90—Buffering arrangements
    • H04L49/901—Buffering arrangements using storage descriptor, e.g. read or write pointers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00—Packet switching elements
    • H04L49/90—Buffering arrangements
    • H04L49/9015—Buffering arrangements for supporting a linked list

Definitions

  • This application relates to the field of computer communication, and in particular, to a Transmission Control Protocol (TCP) packet processing method, a TCP offload engine (TOE) component, and a network device.
  • TCP Transmission Control Protocol
  • TOE TCP offload engine
  • TCP traffic accounts for 90% of the total Internet traffic.
  • CPU central processing unit
  • the TOE technology processes the TCP/IP protocol stack using dedicated hardware, thereby greatly reducing a processing load of the CPU.
  • a dedicated hardware circuit that processes the TCP/IP protocol stack is referred to as a TOE component.
  • US 2004/0133713 A1 provides handling out-of-order TCP segments and includes placing a first received segment in a host buffer and determining whether a second received segment is an in-order or out-of-order segment;
  • US 7523179 B1 discloses techniques, systems, and apparatus for conducting direct data placement of network message data to a final destination in a user buffer;
  • US 2008/0133798 A1 discloses a hardware apparatus for receiving a packet for TCP offload engine (TOE);
  • WO 2005/104486 A1 provides a method for accelerated TCP stack processing;
  • US 2006/0056435 A1 provides a method of offloading ISCSI TCP/IP processing from a host processing unit, and related ISCSI TCP/IP offload engine.
  • This application provides a TCP packet processing method, a TOE component, and a chip including the TOE component, and a network device including the TOE component, so as to improve efficiency of processing TCP packets.
  • a first aspect of this application provides a TCP packet processing method.
  • the TCP offload engine TOE component obtains a first storage address, where the first storage address is an address of a first storage block in a memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the TOE component obtains the packet header from the first storage block based on the first storage address.
  • the TOE component performs TCP-related protocol processing based on the packet header; and the TCP payload is not read out of the first storage block by the TOE component when the TOE component performs TCP-related protocol processing based on the packet header.
  • a TCP payload of the TCP packet does not need to be read out of a first storage block in which the target TCP packet is stored, thereby avoiding a problem of inefficiency caused by frequently reading the target TCP packet during processing of the target TCP packet.
  • the TCP-related protocol processing is performed based on the packet header of the target TCP packet, the TCP payload of the TCP packet does not need to be read from the first storage block in which the target TCP packet is stored, and in this application, no separate TCP buffer needs to be allocated to different TCP threads, thereby saving storage resources of the memory.
  • the TOE component further sends a second storage address to the central processing unit CPU, where the second storage address is the first storage address; or the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the TOE component sends the second storage address to the CPU, so that the CPU can determine to-be-sent data based on the second storage address, thereby avoiding a waste of interface resources between the TOE component and the CPU caused by directly sending of a TCP packet or a TCP payload to the CPU.
  • the TOE component after obtaining storage addresses of a plurality of TCP packets of a data flow to which the target TCP packet belongs, the TOE component generates a storage chain based on the storage addresses of the plurality of TCP packets, where the second storage address is an address of a start block of the storage chain.
  • the TOE component generates the storage chain based on the storage addresses of the plurality of TCP packets, and sends the address of the start block of the storage chain to the CPU. In this way, the TOE component can send the storage addresses of the plurality of TCP packets to the CPU at a time, thereby further saving the interface resources between the TOE component and the CPU and improving the processing efficiency.
  • the TOE component receives a third storage address sent by the CPU, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored, and the to-be-sent data includes the TCP payload.
  • the TOE component obtains the to-be-sent data based on the third storage address, and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the to-be-sent data includes the TCP payload of the target TCP packet, and the storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent. This indicates that in this implementation, only one storage block needs to be allocated to the TCP packet when the TCP packet is processed. Therefore, this implementation saves the storage space of the memory.
  • the TOE component receives a third storage address sent by a central processing unit CPU, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored.
  • the TOE component obtains the to-be-sent data based on the third storage address; and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the to-be-sent data sent by the CPU does not include the TCP payload of the target TCP packet.
  • the location of the to-be-sent data in the memory does not change, that is, the to-be-sent data can be sent without allocating an additional sending buffer to the to-be-sent data, thereby saving resources of the memory.
  • a second aspect of this application provides a Transmission Control Protocol offload engine TOE component, where the TOE component includes an interface and a processor.
  • the processor obtains a first storage address through the interface, where the first storage address is an address of a first storage block in a memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the processor obtains the packet header from the first storage block based on the first storage address, and performs TCP-related protocol processing based on the packet header; and the TCP payload is not read out of the first storage block by the TOE component when the processor performs TCP-related protocol processing based on the packet header.
  • the processor is further configured to send a second storage address to the central processing unit CPU through the interface, where the second storage address is the first storage address; or the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the processor after obtaining storage addresses of a plurality of TCP packets of a data flow to which the target TCP packet belongs, the processor generates a storage chain based on the storage addresses of the plurality of TCP packets, where the second storage address is an address of a start block of the storage chain.
  • the processor further receives, through the interface, a third storage address sent by the CPU, where the third storage address indicates a storage block in which to-be-sent data determined by the CPU is stored, and the to-be-sent data includes the TCP payload.
  • the processor further obtains the to-be-sent data based on the third storage address, and the storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the processor further receives, through the interface, a third storage address sent by the central processing unit CPU, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored.
  • the processor obtains the to-be-sent data based on the third storage address; and storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • a third aspect of this application provides a chip, where the chip includes the TOE component according to the second aspect or any implementation of the second aspect and a network processor.
  • the chip may further include another component.
  • a fourth aspect of this application provides a network device, where the network device includes the chip according to the third aspect and a central processing unit CPU.
  • a fifth aspect of this application provides another network device, including a Transmission Control Protocol offload engine TOE component and a memory.
  • the memory stores Transmission Control Protocol TCP packets.
  • the TOE component obtains a first storage address, where the first storage address is an address of a first storage block in the memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the TOE component further obtains the packet header from the first storage block based on the first storage address, and performs TCP-related protocol processing based on the packet header; and the TCP payload is not read out of the first storage block by the TOE component when the TOE component performs TCP-related protocol processing based on the packet header.
  • the network device further includes a central processing unit CPU.
  • the TOE component further sends a second storage address to the CPU, where the second storage address is the first storage address; or the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the CPU receives the second storage address, and determines to-be-sent data and a third storage address based on the second storage address, where the third storage address indicates a storage block in which the to-be-sent data is stored, and the to-be-sent data includes the TCP payload.
  • the TOE component After obtaining storage addresses of a plurality of TCP packets of a data flow to which the target TCP packet belongs, the TOE component generates a storage chain based on the storage addresses of the plurality of TCP packets, where the second storage address is an address of a start block of the storage chain.
  • the CPU runs a socket, and the TOE component sends the second storage address to the socket; and the socket is used to receive the second storage address.
  • the CPU runs an application program; and the socket sends the second storage address to the application program and receives the third storage address sent by the application program.
  • the application program receives the second storage address, determines the to-be-sent data and the third storage address based on the second storage address, and sends the third storage address to the socket.
  • the socket sends the third storage address to the TOE component.
  • the TOE component further receives the third storage address, and obtains the to-be-sent data based on the third storage address; and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the network device further includes a central processing unit CPU.
  • the CPU sends a third storage address to the TOE component, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored.
  • the TOE component further obtains the to-be-sent data based on the third storage address; and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • first”, “second”, “third”, “fourth”, and so on are intended to distinguish between different objects but do not indicate a particular order of the objects.
  • first storage address and the second storage address are used to distinguish between different storage addresses, rather than to specify a specific order of the different storage addresses.
  • the network device 100 includes a packet processing engine (packet processing engine, PPE) 101, a buffer management unit (BMU) 102, a memory 103, a network processor (NP) 104, a TOE component 105, and a CPU 106.
  • PPE packet processing engine
  • BMU buffer management unit
  • NP network processor
  • TOE component 105 TOE component 105
  • CPU 106 The PPE 101, the BMU 102, the memory 103, the NP 104, the TOE component 105, and the CPU 106 communicate with each other using a bus 107.
  • the CPU 106 runs a socket and an application program. Functions of these components are described below in detail.
  • the PPE 101, the BMU 102, the NP 104, and the TOE component 105 may be integrated on the same chip, or may be deployed on different chips.
  • the network device 100 may include a gateway, a router, a bridge, a wireless access point, a switch, a firewall, and the like.
  • FIG. 2 is a schematic diagram of a procedure for processing a TCP packet by a network device 100 according to an embodiment of this application.
  • the memory 103 is divided into a plurality of storage areas, such as a BMU storage area, a TCP receiving buffer, a user space storage area, a TCP sending buffer, for use by different components.
  • FIG. 2 is based on an example in which the PPE 101, the BMU 102, the NP 104, and the TOE component 105 are deployed on different chips.
  • the TOE component 105 may be divided into more modules, or may be not divided into modules.
  • the process of transmitting a TCP payload or a complete TCP packet is indicated by a thick solid line with an arrow; the process of transmitting a packet header is indicated by a thin solid line with an arrow; and the process of transmitting another control message is indicated by a dashed line with an arrow.
  • the process of receiving the TCP packet by the network device 100 includes steps S201 to S208.
  • the PPE 101 requests a cache space from the BMU 102, and the BMU 102 allocates the cache space to the PPE 102 based on the application.
  • the allocated cache space is referred to as a BMU storage area in this embodiment.
  • the BMU storage area generally includes a plurality of storage blocks, where each storage block has a corresponding storage address, and the storage block can be found based on the storage address.
  • the PPE 101 receives a TCP packet A, writes the TCP packet A into the BMU storage area, and sends a first storage address to the NP 104 to notify the NP 104 that a new TCP packet needs to be processed.
  • the first storage address is a storage address of the TCP packet A.
  • the first storage address indicates a storage block of the TCP packet A in the BMU storage area.
  • the TCP packet A is any TCP packet.
  • the TCP packet includes a packet header and a payload, and the packet header includes a layer 2 header, a layer 3 header, and a TCP packet header.
  • the NP 104 reads a packet header A of the TCP packet A from the BMU storage area based on the first storage address, and determines, based on information in the packet header A, such as a 5-tuple (source IP address, source port number, protocol type, destination IP address, and destination port number), and a flow table stored in the NP 104, that the TCP packet A is to be processed by the TOE component.
  • a 5-tuple source IP address, source port number, protocol type, destination IP address, and destination port number
  • Each entry of the flow table stores a correspondence between a 5-tuple and an operation.
  • the NP 104 searches the flow table based on the 5-tuple in the packet header to obtain a corresponding operation, where the operation may be forwarding, sending to the CPU, sending to the TOE component, or the like.
  • the NP 104 sends the first storage address to the TOE receiving module 105-1; and the TOE receiving module 105-1 obtains the first storage address, reads the TCP packet A from the BMU storage area based on the first storage address, and processes the TCP packet A.
  • Processing the TCP packet A includes: calculating a checksum of the TCP packet A, separating the packet header A of the TCP packet A from the TCP payload A, and storing the TCP payload A in a temporary buffer (not shown); and performing, based on the packet header A, TCP-related protocol processing such as synchronization, acknowledgement, and re-ordering.
  • the TOE receiving module 105-1 writes the TCP payload A of the TCP packet A into the TCP receiving buffer, and sends a storage address of the TCP payload A in the TCP receiving buffer, that is, a second storage address, to the socket of the CPU.
  • the TOE receiving module 105-1 triggers the BMU 102 to release a storage space corresponding to the first storage address.
  • the socket obtains the second storage address.
  • the socket reads the TCP payload A from the TCP receiving buffer based on the second storage address.
  • the socket writes the TCP payload A to a storage location designated by the application program in the user space storage area, where the designated storage location corresponds to a third storage address.
  • the process of sending the TCP packet by the network device 100 includes steps S209 to S216.
  • the application program invokes a data sending interface of the socket, and sends the third storage address to the socket.
  • This embodiment is described by using sending the TCP payload A as an example.
  • the application program Before invoking the data sending interface of the socket, the application program may process the TCP payload A, or may not process the TCP payload A.
  • the socket reads the TCP payload A from the user space storage area based on the third storage address, writes the TCP payload A into the TCP sending buffer, and sends a fourth storage address to the TOE sending module 105-2, where the fourth storage address indicates a storage location of the TCP payload A in the TCP sending buffer.
  • the TOE sending module 105-2 requests a buffer space from the BMU 102, to obtain a storage block corresponding to the fifth storage address.
  • the TOE sending module 105-2 reads the TCP payload A from the TCP sending buffer based on the fourth storage address, and encapsulates a TCP packet header for the TCP payload A.
  • the TOE sending module 105-2 writes the TCP payload A encapsulated with the TCP packet header into the storage block corresponding to the fifth storage address in the BMU storage area, and sends the fifth storage address to the NP 104.
  • the NP 104 obtains the TCP payload A encapsulated with the TCP packet header from the BMU storage area based on the fifth storage address, and adds a layer 3 header and a layer 2 header to the TCP payload A encapsulated with the TCP packet header to obtain a TCP packet B, and sends the fifth storage address to the PPE 101.
  • the TCP packet B obtained by adding the layer 3 header and the layer 2 header to the payload A encapsulated with the TCP packet header is still stored in the storage block corresponding to the fifth storage address.
  • the PPE 101 After receiving the fifth storage address sent by the NP 104, the PPE 101 reads the TCP packet B from the BMU storage area based on the fifth storage address, and then sends the TCP packet B.
  • the PPE 101 instructs the BMU 102 to release the storage block corresponding to the fifth storage address.
  • the TOE receiving module 105-1 and the TOE sending module 105-2 perform TCP-related processing, and the CPU 106 needs to process only the payload of the TCP packet, thereby reducing the processing load of the CPU 106.
  • this application further provides another TCP packet processing method, where the TCP packet processing method is performed by the TOE component 105.
  • the method includes at least steps S301 to S303.
  • the TOE component 105 obtains a first storage address.
  • the first storage address is an address of a first storage block in the memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the target TCP packet is any TCP packet to be processed; the packet header includes a layer 2 header, a layer 3 header, and a TCP packet header; and the TCP payload is the payload of the target TCP packet.
  • the layer 2 header includes layer 2 protocol-related information, and the layer 3 header may include layer 3 protocol-related information.
  • the layer 2 protocol may be, for example, an Ethernet protocol, a Spanning Tree Protocol (STP), or a Link aggregation Control Protocol (LACP), and so on.
  • the layer 3 protocol may be, for example, Internet Protocol (IP) or Internet Group Control Protocol, and so on.
  • Each storage block has a corresponding storage address, and the storage block can be found based on the storage address.
  • the storage block includes a data description of the TCP packet, a packet header of the TCP packet, and a TCP payload of the TCP packet.
  • the data description records an offset value of the TCP packet header relative to the storage block and a length of the TCP packet header, and the TCP payload can be obtained from the storage block based on the offset value and the length of the TCP packet header.
  • FIG. 3A shows M storage blocks, where each storage block stores one TCP packet.
  • Each storage block includes a data description, a packet header, and a TCP payload.
  • the data description of a TCP packet includes an offset value, a total length of the TCP packet, and a length of the packet header of the TCP packet.
  • the length of the packet header may be the total length of the packet header, or may include a length of a layer 2 header, a length of a layer 3 header, and a length of a TCP packet header.
  • the offset value is an offset of the layer 2 header relative to a start byte of the storage block. For example, in FIG.
  • the offset value is 200 bytes.
  • the layer 2 header can be read from the 201 th byte of the storage block.
  • the size of each storage block is 2000 bytes, which is larger than the length of the TCP packet, and therefore, one TCP packet can be stored in one storage block.
  • a storage block is small, for example, 128 bytes, a single TCP packet may need to occupy a plurality of storage blocks.
  • the packet header of the TCP packet is not included in other storage blocks other than the first storage block.
  • the TOE component receives the first storage address sent by the PPE 101.
  • the TOE component 105 obtains the packet header of the target TCP packet from the first storage block based on the first storage address.
  • the TOE component does not need to process the TCP payload of the TCP packet when processing the TCP protocol stack. Therefore, the TOE component obtains only the packet header of the first TCP packet.
  • the TOE component obtains the packet header based on an offset address in the first storage block and a length of the packet header.
  • the TOE component performs TCP-related protocol processing based on the packet header.
  • the TOE component does not need to migrate a TCP packet or a TCP payload from one buffer to another when performing TCP-related protocol processing. That is, when the TOE component performs TCP-related protocol processing based on the packet header, the TCP payload of the target TCP packet is not read out of the first storage block, and a storage location of the target TCP packet in the memory does not change.
  • the TOE component does not need to process the TCP payload, and only needs to obtain the packet header of the TCP packet from the memory 103, so that a waste of memory bandwidth caused by frequent reading of the TCP payload from the memory can be avoided.
  • this embodiment of this application may include step S304.
  • the TOE component sends a second storage address to the central processing unit CPU.
  • the second storage address indicates a TCP payload that can be processed by the CPU.
  • the second storage address is the first storage address.
  • the TCP payload that can be processed by the CPU is the TCP payload of the target TCP packet.
  • the second storage address indicates a second storage block
  • the second storage block is a start block of at least one storage block
  • the at least one storage block includes the first storage block.
  • the TCP payload that can be processed by the CPU includes payloads of a plurality of TCP packets, where the payloads of the plurality of TCP packets include the TCP payload of the target TCP packet.
  • the CPU processes only the TCP payload, after receiving the second storage address, the CPU learns that the TCP payload in the at least one storage block found based on the second storage address can be processed. Therefore, the second storage address is used to notify the CPU of the TCP payload that can be processed by the CPU.
  • the CPU 106 includes a socket and an application program, where the socket is used to receive the second storage address sent by the TOE component, and send the second storage address to the application program; and the application program is used to determine whether to process the TCP payload that is obtained based on the second storage address.
  • the application program in the CPU 106 obtains the TCP payload based on the second storage address and processes the TCP payload. In another implementation, the application program in the CPU 106 does not need to process the TCP payload.
  • the TOE component 105 after receiving storage addresses of a plurality of TCP packets of a data flow to which the target TCP packet belongs, the TOE component 105 generates a first storage chain based on the storage addresses of the plurality of TCP packets of a data flow to which the target TCP packet belongs, where the second storage address received by the central processing unit is an address of the first storage chain, and the address of the first storage chain is an address of a start block of the first storage chain. Further, as shown in FIG. 3 , this embodiment of this application may include step S305.
  • the TOE component obtains the first storage address sent by the CPU.
  • the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored, so as to indicate the to-be-sent data.
  • the to-be-sent data may include a TCP payload processed by the application program in the CPU 106, or may include a TCP payload that does not need to be processed by the application program in the CPU 106.
  • the to-be-sent data may include a TCP payload of at least one TCP packet.
  • the to-be-sent data includes the TCP payload in S301.
  • the to-be-sent data may not include the TCP payload in S301.
  • the third storage address is the first storage address. In this case, the third storage address indicates only the first storage block, that is, the to-be-sent data is the TCP payload of the target TCP packet in S301.
  • the third storage address indicates a third storage block
  • the third storage block is a start block of at least one storage block
  • the at least one storage block may or may not include the first storage block.
  • the third storage address indicates a plurality of storage blocks including the first storage block
  • the first storage block is a start block in the plurality of storage blocks
  • the third storage address is the first storage address.
  • the third storage address indicates a plurality of storage blocks including the first storage block, and the first storage block is not a start block in the plurality of storage blocks, the third storage address different from the first storage address.
  • the TOE component determines the to-be-sent data based on the third storage address, and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the procedure for processing the to-be-sent data by the TOE component includes steps S306 to S309.
  • the TOE component determines window data based on the third storage address, where the window data is a part or all of the to-be-sent data.
  • the window data refers to data that can be sent by the TOE component at a time.
  • the procedure for determining the window data by the TOE component will be described later in detail.
  • the TOE component sends a fourth storage address of the window data, where the fourth storage address indicates a storage block of the window data in the memory.
  • a storage location of the window data in the memory does not change before the window data is successfully sent.
  • the window data as an example, the TCP payload of the target TCP packet is stored in the first storage block before the TCP payload is successfully sent.
  • the TOE component receives a TCP acknowledgement message, where the TCP acknowledgement message indicates that the window data is successfully sent.
  • the TOE component needs to perform S306 to S308 a plurality of times.
  • the TOE component instructs the memory to release a memory resource corresponding to the window data.
  • the TOE component after receiving the message indicating that the window data is successfully sent, the TOE component immediately instructs the memory to release the memory resource corresponding to the window data. In another implementation, after receiving TCP acknowledgement messages corresponding to all window data included in the to-be-sent data, the TOE component instructs the memory to release the storage block corresponding to the fourth storage address. In the foregoing implementation of this application, the storage block used by the network device to store a received TCP packet is reused, and the network device does not need to allocate a separate receiving buffer and a sending buffer to the TOE component. In addition, after sending the to-be-sent data determined by the CPU, the TOE component instructs the memory 103 to release the storage block occupied by the to-be-sent data, thereby avoiding a waste of memory resources.
  • an embodiment of this application further provides a schematic diagram of a procedure for processing a TCP packet by another network device 100.
  • the processing procedure includes steps S401 to S413.
  • the process of transmitting a TCP payload or a complete TCP packet is indicated by a thick solid line with an arrow; the process of transmitting a packet header is indicated by a thin solid line with an arrow; and the process of transmitting another control packet is indicated by a dashed line with an arrow.
  • corresponding storage areas in the memory 103 do not need to be allocated to different components. Mutual reference may be made to the method shown in FIG. 3 and the procedure shown in FIG. 4 .
  • the PPE 101 requests a cache space from the BMU 102, and the BMU 102 allocates the cache space to the PPE 102 from the memory 103 based on this application, where the allocated cache space is referred to as a BMU storage area in this embodiment.
  • the PPE 101, the NP 104, the TOE component 105, and the CPU 106 share the BMU storage area.
  • the BMU storage area is further divided into a plurality of storage blocks, and each storage block corresponds to one storage address.
  • the plurality of storage blocks are of the same size.
  • each storage block is capable of storing a complete TCP packet.
  • a size of the storage block may be set at will, and when the size of the storage block is less than that of a TCP packet, the TCP packet may be stored in a plurality of storage blocks.
  • the PPE 101 receives a target TCP packet, performs a TCP check on the target TCP packet, writes the target TCP packet into a first storage block in the BMU storage area after the TCP check is passed, and sends a first storage address of the first storage block to the NP 104.
  • the target TCP packet includes a TCP packet header and a TCP payload.
  • the first storage block may be found based on the first storage address.
  • the first storage block includes a data description, and the data description includes a packet header and a TCP payload that are of the target TCP packet.
  • the data description includes an offset value, a length of the target TCP packet, and a length of the packet header; and the offset value is an offset of the packet header of the target TCP packet in the first storage block, for example, in FIG. 3A , the offset value is 200 bytes.
  • the PPE 101 writes the target TCP packet to the BMU storage area using the mbuf structure.
  • one mbuf structure is stored in one storage block.
  • FIG. 5 is a schematic diagram of an mbuf structure (mbuf for short).
  • a total length of mbuf in FIG. 5 is 1000 bytes, including a 20-byte header (corresponding to the data description in FIG. 3A ). Therefore, one mbuf can store a maximum of 980 bytes of data.
  • the packet needs to be stored in two mbufs (that is, two storage blocks).
  • the total length of mbuf may be another length, for example, 2000 bytes.
  • a header of the mbuf may alternatively be of another length, for example, 100 bytes.
  • the header of the mbuf may include a plurality of fields.
  • m_next points to the next mbuf storing the same packet, and is valid only when a packet is stored in a plurality of mbufs; otherwise, m_next is null.
  • m_nextpkt points to the first mbuf of another packet.
  • m_len indicates a size of data stored in the mbuf, for example, 80 bytes in FIG. 5 .
  • m_data is a pointer that points to stored data.
  • m_type indicates a type of data included in the mbuf; and in FIG. 5 , m_type is MT_header, indicating that the data includes a TCP packet header.
  • m_flags may be M_PKTHDR, 0, or M_EXT, where M_PKTHDR indicates that the mbuf is the first in the mbuf linked list, that is, the header of the linked list; 0 indicates that the mbuf includes only data; and M_EXT indicates that the mbuf uses an external cluster to store data of relatively large data.
  • the packet header of the first mbuf of a packet may include m_pkthdr.len and m_pkthdr.rcvif, where m_pkthdr.len indicates a length of the packet header of the packet; and m_pkthdr.rcvif indicates a pointer that points to an interface structure.
  • m_pkthdr.len and m_pkthdr.rcvif are not needed. The mbuf shown in FIG.
  • the data portion includes a packet header; and the data portion stores a layer 2 header of 14 bytes, a layer 3 header of 20 bytes, a TCP packet header of 20 bytes, and a payload of 26 bytes, and the gray portion represents unoccupied bytes in the mbuf.
  • the NP 104 reads the packet header of the target TCP packet from the first storage block in the BMU storage area based on the first storage address, and determines, based on information in the packet header, that the target TCP packet needs to be processed by the TOE component 105.
  • the flow characteristic included in the packet header corresponds to the action of forwarding to the TOE component in the flow table
  • the NP 104 determines that the target TCP packet needs to be processed by the TOE component 105.
  • the flow characteristic may be a flow identifier, or at least one of a 5-tuple (source IP address, destination IP address, source port number, destination port number, and transport layer protocol).
  • the NP 104 sends the first storage address to the TOE component 105.
  • the TOE component 105 receives the first storage address, obtains the packet header of the target TCP packet from the first storage block based on the first storage address, and performs TCP-related protocol processing based on the packet header.
  • TCP-related protocol processing based on the packet header, a storage location of the target TCP packet in the BMU storage area does not change, and the payload of the target TCP packet is not read out of the first storage block by the TOE component 105.
  • the NP 104 sends the first storage address to the TOE receiving module 105-1 in the TOE component 105.
  • the TCP-related protocol processing includes one or more of state transition, congestion control, re-ordering, lost packet retransmission, round-trip time (RTT) calculation, and the like.
  • TCP-related protocol processing may be performed using any algorithm or manner well known to those skilled in the art.
  • the TOE component 105 sends a second storage address to the CPU 106.
  • the second storage address indicates a TCP payload that can be processed by the CPU.
  • the TOE component 105 sends the second storage address to the socket of the CPU 106 by using the TOE receiving module 105-1.
  • the second storage address is the first storage address; in another implementation, the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the TOE component 105 records a first storage address of the target TCP packet; and after determining storage addresses of a plurality of TCP packets of a data flow to which the target TCP packet belongs, the TOE component 105 generates a first storage chain based on the storage addresses of the plurality of TCP packets, and sends an address of the first storage chain, that is, an address of a start block of the first storage chain, to the CPU.
  • the plurality of TCP packets include the target TCP packet.
  • the address of the first storage chain is the second storage address.
  • the address of the first storage chain is used by the CPU to obtain the TCP payload in each storage block included in the first storage chain.
  • the first storage chain is an mbuf chain.
  • FIG. 6 is a schematic structural diagram of an mbuf chain.
  • the mbuf chain indicates two TCP packets: a TCP packet A and a TCP packet B.
  • the TCP packet A occupies two mbufs
  • the TCP packet B occupies one mbuf
  • the m_nextpkt pointer of the TCP packet A points to the m_nextpkt of the TCP packet B
  • the m_nextpkt of the TCP packet B is null.
  • the socket of the CPU 106 receives the second storage address, and sends the second storage address to the application program.
  • the socket receives the address of the mbuf chain through an mbuf_recv interface (an interface that is extended to be capable of receiving the address of the mbuf chain in this application).
  • the application program sends a third storage address to the socket.
  • the third storage address indicates a storage block in which the to-be-sent data determined by the application program is stored.
  • the to-be-sent data includes the TCP payload of the target TCP packet. In another implementation, the to-be-sent data does not include the TCP payload of the target TCP packet.
  • the application program may process the TCP payload indicated by the second storage address, for example, modify the content of the TCP payload, or may not process the TCP payload indicated by the second storage address.
  • the application program when the to-be-sent data determined by the application program includes payloads of a plurality of TCP packets, or when the to-be-sent data determined by the application program is stored in a plurality of mbufs, the application program generates a second storage chain based on the to-be-sent data, invokes an mbuf_send interface (an interface that is extended to be capable of sending the address of the mbuf chain in this application) of the socket, and sends an address of the second storage chain to the socket through the mbuf_send interface.
  • the address of the second storage chain is an address of a start block of the second storage chain.
  • the second storage chain may be the same as or different from the first storage chain.
  • the address of the second storage chain is the third storage address.
  • S406 and S407 may be summarized as follows:
  • the CPU 106 receives the second storage address, and determines, based on the second storage address, the third storage address of the to-be-sent data and the storage block in which the to-be-sent data is stored.
  • the to-be-sent data is all or a part of the TCP payload indicated by the second storage address.
  • the third storage address and the second storage address may be the same or different.
  • the to-be-sent data includes the TCP payload of the target TCP packet.
  • the CPU 106 sends the third storage address to the TOE component 105.
  • the socket of the CPU 106 sends the third storage address to the TOE sending module 105-2 in the TOE component 105.
  • the TOE component 105 modifies the TCP packet header corresponding to each TCP payload indicated by the third storage address.
  • the TOE sending module 105-2 finds each to-be-sent TCP payload based on the third storage address, and modifies the TCP packet header corresponding to the TCP payload a needed, for example, modifies a TCP port number in the TCP packet header.
  • S409 is an optional step in this application.
  • the TOE component 105 determines window data based on the third storage address, where the window data is a part or all of the to-be-sent data.
  • the TOE component 105 sends a fourth storage address to the NP 104, where the fourth storage address indicates a storage block of the window data in the memory.
  • the TOE sending module 105-2 in the TOE component 105 determines the window data based on a congestion window of the network device 100, and a peer-end receiving window, and the to-be-sent data stored in the storage block corresponding to the third storage address.
  • the TOE component sending module 105-2 first determines the amount of the window data based on the congestion window of the network device 100 and the peer-end receiving window, but determines, based on the amount of the window data, the window data from the to-be-sent data stored in the storage block corresponding to the third storage address.
  • the amount of the window data may be the quantity of mbufs, or the quantity of bytes that need to be sent.
  • the fourth storage address is determined based on the window data sent each time.
  • the to-be-sent data are stored in five mbufs: mbuf 1, mbuf 2, mbuf 3, mbuf 4, and mbuf 5.
  • the TOE component 105 determines that the data in three mbufs can be sent at the first time based on the congestion window of the network device 100 and a peer-end receiving window; and then generates a third storage chain based on mbuf 1, mbuf 2, and mbuf 3, and sends the address of the third storage chain (that is, the storage address of the storage block in which mbuf 1 is located) as the fourth storage address to the NP 104.
  • the TOE component 105 may constitute the remaining two mbufs, namely, mbuf 4 and mbuf 5, into a fourth storage chain, and send an address of the fourth storage chain (namely, a storage address of a storage block in which mbuf 4 is located) as the fourth storage address to the NP 104.
  • the window data is a part of data in an mbuf
  • the TOE component 105 may split the mbuf into a plurality of mbufs.
  • Each of the plurality of new mbufs obtained through splitting occupies one storage block
  • a first mbuf in the plurality of mbufs includes the window data
  • the fourth storage address is a storage address of a storage block in which the first mbuf is located.
  • the NP 104 receives the fourth storage address, and modifies the layer 3 header and the layer 2 header in a storage block corresponding to the fourth storage address, to obtain a modified TCP packet.
  • the NP 104 sends the fourth storage address to the PPE 101.
  • the PPE 101 receives the fourth storage address, reads the modified TCP packet from the storage block corresponding to the fourth storage address, calculates a checksum, adds the calculated checksum to the modified TCP packet, and sends the modified TCP packet.
  • the modified TCP packet is still stored in the storage block corresponding to the fourth storage address.
  • the TOE component 105 receives a TCP acknowledgement message (through the TOE receiving module 105-1), where the TCP acknowledgement message is used to indicate the data received by the peer device.
  • the TOE component 105 confirms, based on the TCP acknowledgement message, that the window data is successfully sent, and instructs the BMU 102 to release the storage block corresponding to the fourth storage address.
  • S414 is an implementation of S308 and S309.
  • the length of an Ethernet packet is 64 bytes to 1500 bytes, and the length of a packet header is 20 bytes to 64 bytes.
  • the NP 104 and the TOE component 105 need to read only the packet header of the TCP packet when processing the TCP packet, and do not need to frequently read the payload of the TCP packet from the BMU storage area, so that access bandwidth of the memory 103 can be reduced, and processing efficiency can be improved.
  • this application further provides a TOE component 700, where the TOE component 700 includes an interface 701 and a processor 702.
  • the interface 701 is used by the TOE component 100 to communicate with another component of the network device.
  • the processor 702 obtains a first storage address through the interface 701, where the first storage address is an address of a first storage block in a memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the processor 702 obtains the packet header of the target TCP packet from the first storage block based on the first storage address.
  • the processor 702 performs TCP-related protocol processing based on the packet header; and the TCP payload is not read out of the first storage block by the TOE component when the processor 702 performs TCP-related protocol processing based on the packet header.
  • the processor 702 is further configured to send a second storage address to the central processing unit CPU through the interface 701, where the second storage address is the first storage address; or the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the processor 702 further generates a storage chain based on the storage addresses of the plurality of TCP packets, where the second storage address is an address of a start block of the storage chain.
  • the processor 702 further receives, through the interface 701, a third storage address sent by the CPU, where the third storage address indicates a storage block in which to-be-sent data determined by the CPU is stored, and the to-be-sent data includes the TCP payload. Further, the processor 702 determines the to-be-sent data based on the third storage address, and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the processor 702 further receives, through the interface 701, a third storage address sent by the central processing unit CPU, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored. Further, the processor 702 determines the to-be-sent data based on the third storage address, and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • This application further provides a chip, where the chip includes the TOE component shown in FIG. 7 and a network processor.
  • the network processor may be the NP 104 in FIG. 1 , FIG. 2 , or FIG. 3 .
  • the chip may include one of or both the PPE 101 and the BMU 102 in FIG. 1 .
  • the network device includes a TOE component 801, a memory 802, and a CPU 803, where the CPU 803 runs a socket and an applications.
  • the TOE component 801, the memory 802, and the CPU 803 communicate with each other using a bus 804.
  • the memory 802 stores Transmission Control Protocol TCP packets.
  • the TOE component 801 obtains a first storage address, where the first storage address is an address of a first storage block in the memory, the first storage block stores a target TCP packet, and the target TCP packet includes a packet header and a TCP payload.
  • the TOE component 801 performs TCP-related protocol processing based on the packet header; and the TCP payload is not read out of the first storage block by the TOE component when the TOE component 801 performs TCP-related protocol processing based on the packet header.
  • the TOE component 801 is further configured to send a second storage address to the CPU 803, where the second storage address is the first storage address; or the second storage address indicates a second storage block, the second storage block is a start block of at least one storage block, and the at least one storage block includes the first storage block.
  • the CPU 803 receives the second storage address, and determines to-be-sent data and a third storage address based on the second storage address, where the third storage address indicates a storage block in which the to-be-sent data is stored, and the to-be-sent data includes the TCP payload.
  • the TOE component 801 further generates a storage chain based on the storage addresses of the plurality of TCP packets, where the second storage address is an address of a start block of the storage chain.
  • the TOE component 801 sends the second storage address to the socket.
  • the socket receives the second storage address, sends the second storage address to the application program, and receives the third storage address sent by the application program.
  • the application program receives the second storage address, determines the to-be-sent data and the third storage address based on the second storage address, and sends the third storage address to the socket.
  • the socket sends the third storage address to the TOE component 801.
  • the TOE component 801 further receives the third storage address, and obtains the to-be-sent data based on the third storage address; and a storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the CPU 803 sends a third storage address to the TOE component, where the third storage address indicates a storage block in which the to-be-sent data determined by the CPU is stored.
  • the TOE component 801 further obtains the to-be-sent data based on the third storage address; and the storage location of the to-be-sent data in the memory does not change before the to-be-sent data is successfully sent.
  • the TOE component, the chip, and the network device in this application process a TCP packet, only a packet header of the TCP packet needs to be read, and a payload of the TCP packet does not need to be frequently read from a memory, so that access bandwidth of the memory can be reduced, and processing efficiency can be improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
EP19867965.6A 2018-09-27 2019-09-06 Method for processing tcp message, toe assembly, and network device Active EP3846405B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811134308.XA CN110958213B (zh) 2018-09-27 2018-09-27 处理tcp报文的方法、toe组件以及网络设备
PCT/CN2019/104721 WO2020063298A1 (zh) 2018-09-27 2019-09-06 处理tcp报文的方法、toe组件以及网络设备

Publications (3)

Publication Number Publication Date
EP3846405A1 EP3846405A1 (en) 2021-07-07
EP3846405A4 EP3846405A4 (en) 2021-09-22
EP3846405B1 true EP3846405B1 (en) 2023-11-15

Family

ID=69951167

Family Applications (1)

Application Number Title Priority Date Filing Date
EP19867965.6A Active EP3846405B1 (en) 2018-09-27 2019-09-06 Method for processing tcp message, toe assembly, and network device

Country Status (4)

Country Link
US (1) US11489945B2 (zh)
EP (1) EP3846405B1 (zh)
CN (1) CN110958213B (zh)
WO (1) WO2020063298A1 (zh)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112019645B (zh) * 2020-07-06 2021-07-30 中科驭数（北京）科技有限公司 基于toe的网络地址管理方法及装置
CN112073434B (zh) * 2020-09-28 2022-06-07 山东产研集成电路产业研究院有限公司 降低基于toe的高频交易终端接收通道传输延迟的方法
CN112953967A (zh) * 2021-03-30 2021-06-11 扬州万方电子技术有限责任公司 网络协议卸载装置和数据传输系统
CN113179327B (zh) * 2021-05-14 2023-06-02 中兴通讯股份有限公司 基于大容量内存的高并发协议栈卸载方法、设备、介质
CN115460300A (zh) * 2021-06-08 2022-12-09 中兴通讯股份有限公司 数据处理方法、toe硬件及计算机可读存储介质
CN115883672A (zh) * 2021-08-11 2023-03-31 大唐联仪科技有限公司 组包方法、数据传输方法、装置、电子设备及存储介质
CN115941762A (zh) * 2021-09-03 2023-04-07 华为技术有限公司 一种数据传输方法、电子设备和装置
CN113824706B (zh) * 2021-09-10 2023-07-25 杭州迪普信息技术有限公司 报文解析方法及网络设备
CN114422617B (zh) * 2021-12-30 2023-07-25 苏州浪潮智能科技有限公司 一种报文处理方法、系统及计算机可读存储介质
CN118283135A (zh) * 2024-05-30 2024-07-02 井芯微电子技术(天津)有限公司 Toe组件及其处理数据的方法
CN118283134A (zh) * 2024-05-30 2024-07-02 井芯微电子技术(天津)有限公司 Toe组件及其处理数据的方法

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7397800B2 (en) * 2002-08-30 2008-07-08 Broadcom Corporation Method and system for data placement of out-of-order (OOO) TCP segments
US7313623B2 (en) * 2002-08-30 2007-12-25 Broadcom Corporation System and method for TCP/IP offload independent of bandwidth delay product
US20050060538A1 (en) * 2003-09-15 2005-03-17 Intel Corporation Method, system, and program for processing of fragmented datagrams
US7275152B2 (en) * 2003-09-26 2007-09-25 Intel Corporation Firmware interfacing with network protocol offload engines to provide fast network booting, system repurposing, system provisioning, system manageability, and disaster recovery
US7562158B2 (en) * 2004-03-24 2009-07-14 Intel Corporation Message context based TCP transmission
US7668165B2 (en) * 2004-03-31 2010-02-23 Intel Corporation Hardware-based multi-threading for packet processing
US7783769B2 (en) * 2004-03-31 2010-08-24 Intel Corporation Accelerated TCP (Transport Control Protocol) stack processing
CN1747444A (zh) * 2004-09-10 2006-03-15 国际商业机器公司 数据处理系统网络中从主机单元分担数据流的方法及引擎
US7620071B2 (en) * 2004-11-16 2009-11-17 Intel Corporation Packet coalescing
US7523179B1 (en) * 2004-12-14 2009-04-21 Sun Microsystems, Inc. System and method for conducting direct data placement (DDP) using a TOE (TCP offload engine) capable network interface card
US7475167B2 (en) * 2005-04-15 2009-01-06 Intel Corporation Offloading data path functions
US8028071B1 (en) * 2006-02-15 2011-09-27 Vmware, Inc. TCP/IP offload engine virtualization system and methods
US7849214B2 (en) * 2006-12-04 2010-12-07 Electronics And Telecommunications Research Institute Packet receiving hardware apparatus for TCP offload engine and receiving system and method using the same
JP4921142B2 (ja) * 2006-12-12 2012-04-25 キヤノン株式会社 通信装置
US8194667B2 (en) * 2007-03-30 2012-06-05 Oracle America, Inc. Method and system for inheritance of network interface card capabilities
US8006297B2 (en) * 2007-04-25 2011-08-23 Oracle America, Inc. Method and system for combined security protocol and packet filter offload and onload
US8316276B2 (en) * 2008-01-15 2012-11-20 Hicamp Systems, Inc. Upper layer protocol (ULP) offloading for internet small computer system interface (ISCSI) without TCP offload engine (TOE)
KR101221045B1 (ko) * 2008-12-22 2013-01-10 한국전자통신연구원 패킷 처리 방법 및 이를 이용한 ｔｏｅ 장치
KR101712199B1 (ko) * 2010-03-02 2017-03-03 삼성전자주식회사 메시징 서비스와 소셜 네트워크 서비스 간의 상호 연동을 통한 연락처 제공 장치 및 방법
CN103546424A (zh) * 2012-07-10 2014-01-29 华为技术有限公司 一种tcp数据传输方法、tcp卸载引擎及系统
US9154427B2 (en) * 2012-12-31 2015-10-06 Emulex Corporation Adaptive receive path learning to facilitate combining TCP offloading and network adapter teaming
US9286225B2 (en) * 2013-03-15 2016-03-15 Saratoga Speed, Inc. Flash-based storage system including reconfigurable circuitry
CN106034084B (zh) * 2015-03-16 2020-04-28 华为技术有限公司 一种数据传输方法及装置
CN106330788B (zh) * 2016-08-19 2018-05-22 北京网迅科技有限公司杭州分公司 报文分片传输方法和装置
CN106789708B (zh) * 2016-12-06 2020-10-09 中国电子科技集团公司第三十二研究所 Tcp/ip卸载引擎中的多通道处理方法
CN109714302B (zh) * 2017-10-25 2022-06-14 阿里巴巴集团控股有限公司 算法的卸载方法、装置和系统

Also Published As

Publication number Publication date
CN110958213B (zh) 2021-10-22
WO2020063298A1 (zh) 2020-04-02
US11489945B2 (en) 2022-11-01
EP3846405A4 (en) 2021-09-22
EP3846405A1 (en) 2021-07-07
US20210218831A1 (en) 2021-07-15
CN110958213A (zh) 2020-04-03

Similar Documents

Publication Publication Date Title
EP3846405B1 (en) Method for processing tcp message, toe assembly, and network device
US8311059B2 (en) Receive coalescing and automatic acknowledge in network interface controller
US11716409B2 (en) Packet transmission method and apparatus
EP2928135B1 (en) Pcie-based host network accelerators (hnas) for data center overlay network
CN101217493B (zh) 一种tcp数据包的传输方法
WO2023005773A1 (zh) 基于远程直接数据存储的报文转发方法、装置、网卡及设备
EP1868093B1 (en) Method and system for a user space TCP offload engine (TOE)
US6757746B2 (en) Obtaining a destination address so that a network interface device can write network data without headers directly into host memory
US9276854B2 (en) Scaling egress network traffic
US7953093B2 (en) TCP/IP reordering
WO2021013046A1 (zh) 通信方法和网卡
CN112187612A (zh) 高性能、可扩展和无掉话的数据中心交换结构
US11979340B2 (en) Direct data placement
US8539112B2 (en) TCP/IP offload device
US8539089B2 (en) System and method for vertical perimeter protection
US20070291782A1 (en) Acknowledgement filtering
WO2017162117A1 (zh) 一种集群精确限速方法和装置
US9961147B2 (en) Communication apparatus, information processor, communication method, and computer-readable storage medium
US20060101090A1 (en) Method and system for reliable datagram tunnels for clusters
CN106789708B (zh) Tcp/ip卸载引擎中的多通道处理方法
JP2006180480A (ja) 動的アドレスを使用してルーティングを実行するネットワークシステム及びその方法
US10298494B2 (en) Reducing short-packet overhead in computer clusters
JP2000235536A (ja) データ通信方式及び装置
CN114443281A (zh) 一种网卡负载调整方法、装置、设备及可读存储介质
US7290055B2 (en) Multi-threaded accept mechanism in a vertical perimeter communication environment

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20210331

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

A4 Supplementary search report drawn up and despatched

Effective date: 20210825

RIC1 Information provided on ipc code assigned before grant

Ipc: H04L 29/06 20060101AFI20210819BHEP

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20220704

REG Reference to a national code

Ref document number: 602019041667

Country of ref document: DE

Ref country code: DE

Ref legal event code: R079

Free format text: PREVIOUS MAIN CLASS: H04L0029060000

Ipc: H04L0069120000

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: H04L 49/901 20220101ALI20230622BHEP

Ipc: H04L 47/193 20220101ALI20230622BHEP

Ipc: H04L 69/22 20220101ALI20230622BHEP

Ipc: H04L 69/163 20220101ALI20230622BHEP

Ipc: H04L 69/16 20220101ALI20230622BHEP

Ipc: H04L 69/12 20220101AFI20230622BHEP

INTG Intention to grant announced

Effective date: 20230711

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602019041667

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG9D

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240216

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1632818

Country of ref document: AT

Kind code of ref document: T

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240216

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240215

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240215

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602019041667

Country of ref document: DE

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20240730

Year of fee payment: 6

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20240801

Year of fee payment: 6